CN107918633B - Sensitive public opinion content identification method and early warning system based on semantic analysis technology - Google Patents
Sensitive public opinion content identification method and early warning system based on semantic analysis technology Download PDFInfo
- Publication number
- CN107918633B CN107918633B CN201710179529.8A CN201710179529A CN107918633B CN 107918633 B CN107918633 B CN 107918633B CN 201710179529 A CN201710179529 A CN 201710179529A CN 107918633 B CN107918633 B CN 107918633B
- Authority
- CN
- China
- Prior art keywords
- sensitive
- words
- word
- content
- emotional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a sensitive public opinion content identification method and an early warning system based on semantic analysis technology, wherein the method is characterized in that a sensitive word vector library is added outside a Chinese participle reference word library, sensitive words are classified, each type of sensitive word is provided with a core word as a reference word, and simultaneously, the core word is used as a source node to set distance vectors from other similar words to the reference word; carrying out voice recognition on the audio file to recognize sensitive words and related emotional words; performing clustering analysis, identifying sensitive words and emotional words related to semantics, and performing semantic analysis and judgment; and identifying and outputting the sensitive content. The invention establishes a sensitive word vector library on the basis of the traditional natural language word library, and establishes a vector distance relation between similar sensitive words. In the field of practical application, for example, for real-time call content or classroom teaching content, sensitive content identification and early warning can be automatically carried out. The method can realize the judgment of sensitive semantics, greatly improve the accuracy and further realize the monitoring of sensitive public opinion content.
Description
Technical Field
The invention relates to the technical field of information technology, information security and education, in particular to a sensitive public opinion content identification method and an early warning system based on a semantic analysis technology.
Background
Speech recognition technology and natural language processing are widely used in various fields such as communications, industry, home appliances, car networking, medical care, home services, consumer electronics, and the like.
In the field of information security, particularly in the sensitive content identification in the communication process, the current main method only depends on sensitive word labeling and word frequency statistics, and no analysis exists on the meaning, so that a relatively high false alarm rate exists.
In the technical field of education, the application of the voice recognition technology is limited to spoken language evaluation and voice translation, and classroom content recognition and early warning are lacked. In the field of political thought class classroom teaching, currently, the teaching examination is mainly carried out in a manual class listening (on-site class listening or video review) mode, and the efficiency is very low.
Disclosure of Invention
The present invention aims to solve the above technical problem at least to some extent.
The invention mainly aims to provide a sensitive public opinion content identification method based on semantic analysis technology, which can realize the identification and accurate analysis of sensitive content on the basis of the result of basic semantic analysis, and the accuracy is greatly improved.
The invention further aims to provide a sensitive public opinion content early warning system based on semantic analysis technology, which realizes the identification, accurate analysis and output of sensitive content.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a sensitive public opinion content identification method based on semantic analysis technology comprises the following steps:
s1: establishing a sensitive word vector word bank: importing a sensitive word vector library, classifying the sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node;
s2: and (3) voice recognition processing: carrying out voice recognition on the audio file to recognize sensitive words and related emotional words;
s3: and (3) positioning sensitive content: performing clustering analysis, identifying sensitive words and emotional words related to semantics, and performing semantic correction;
s4: outputting an analysis result: and outputting the sensitive content.
In a preferred embodiment, the step S1 of establishing the sensitive thesaurus includes the following steps:
s1.1: importing a common Chinese word segmentation reference word library;
s1.2: establishing a special sensitive word vector word library;
s1.3: classifying the sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node.
In a preferred embodiment, in step S2, the speech recognition process includes the following steps:
s2.1: carrying out voice recognition on the audio file by utilizing a voice recognition engine, and converting the audio file into a text;
s2.2: completing the natural language processing procedures such as word segmentation, part of speech tagging, basic semantic recognition and the like, and storing the natural language processing procedures in a database;
s2.3: and identifying and marking the sensitive words and the related emotional words.
In a preferred embodiment, in step S3, the sensitive content locating step includes the following steps:
s3.1: performing clustering analysis, and identifying sensitive words and emotional words related to semantics;
s3.2: performing measurement calculation of the associated sensitive words and the emotional words, and performing semantic analysis and judgment; on the basis of a traditional semantic analysis algorithm, two key elements of time and distance vectors are introduced, and the accuracy of sensitive content identification is improved.
S3.3: and realizing the identification, positioning and labeling of sensitive content.
In a preferred scheme, in step S3.2, the metric calculation of the associated sensitive word and the emotion word is specifically performed as follows: and calculating the difference between the distance vectors of the sensitive words, and if the difference is smaller than a preset value, performing measurement calculation according to the time sequence and the word sequence of the sensitive words and the emotional words.
In a preferred embodiment, the outputting of the analysis result in step S4 includes the following steps:
s4.1: the user self-defines a threshold value aiming at the occurrence frequency of the sensitive words;
s4.2: the user self-defines an early warning output mode, including WeChat, short message, mail and webpage presentation;
s4.3: and labeling and tracing the sensitive content.
A sensitive public opinion content early warning system based on semantic analysis technology comprises:
sensitive word bank: the system comprises a Chinese word segmentation reference word library, a distance vector calculation module and a distance vector calculation module, wherein the distance vector calculation module is used for importing a Chinese word segmentation reference word library, classifying sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference words by using the core word as a source node;
the voice recognition processing module: the voice recognition method is used for carrying out voice recognition on the audio file and recognizing sensitive words and related emotional words;
the sensitive content positioning module: the method is used for carrying out clustering analysis, identifying sensitive words and emotional words related to semantics and carrying out semantic correction;
and an output module of the analysis result: for identifying and outputting sensitive content.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: the invention provides a sensitive public opinion content identification method based on semantic analysis technology, which comprises the steps of importing a sensitive word vector word library, classifying sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node; carrying out voice recognition on the audio file to recognize sensitive words and related emotional words; performing clustering analysis, identifying sensitive words and emotional words related to semantics, performing measurement calculation of related sensitive words and emotional words, and performing semantic analysis and judgment; and identifying and outputting the sensitive content. The invention establishes a sensitive word vector library on the basis of the traditional natural language word library, and establishes a vector distance relation between similar sensitive words. In the practical application field, for example, for real-time call content (information security field) or classroom teaching content (education technical field), sensitive content identification and early warning can be automatically carried out. The method can realize the judgment of sensitive semantics, greatly improve the accuracy and further realize the monitoring of sensitive public opinion content.
The result is applied to the field of information security, and sensitive content analysis and early warning of real-time conversation can be automatically identified. The results are applied to the technical field of education, and sensitive content analysis and early warning of classroom teaching contents can be achieved. The method is applied to the field of information security, and can automatically identify the sensitive content analysis of real-time conversation and perform early warning. The method is applied to the technical field of education, can realize sensitive content analysis of classroom teaching contents, and performs early warning. Especially, when the intelligent education system is applied to the ideological and political education class, the intelligent education system can accurately guide public opinions for controlling the ideological and political education in class, and has positive effects on vigorously promoting the mental civilization construction, promoting the healthy atmosphere in class and cultivating students with correct three views in China.
The invention also provides a sensitive public opinion content early warning system based on the semantic analysis technology, which realizes the identification, accurate analysis and output of sensitive content.
Drawings
Fig. 1 is a flowchart of a sensitive public opinion content identification method based on semantic analysis technology according to the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
First, the related terms related to the present invention are introduced:
1. artificial Intelligence (AI, Artificial Intelligence)
Is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence, a field of research that includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. Since the birth of artificial intelligence, theories and technologies become mature day by day, and application fields are expanded continuously, so that science and technology products brought by the artificial intelligence in the future can be assumed to be 'containers' of human intelligence.
2. Speech recognition
Speech recognition technology is a high technology that allows machines to convert speech signals into corresponding text or commands through a recognition and understanding process. The voice recognition technology mainly comprises three aspects of a feature extraction technology, a pattern matching criterion and a model training technology.
3. Natural Language Processing (NLP, Natural Language Processing)
Natural language processing is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics.
Example 1
As shown in fig. 1, a sensitive public opinion content identification method based on semantic analysis technology includes the following steps:
s1: establishing a sensitive word vector word bank: importing a sensitive word vector word library, classifying sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node;
in step S1, the creating of the sensitive thesaurus includes the following steps:
s1.1: importing a common Chinese word segmentation reference word library;
s1.2: establishing a special sensitive word vector library;
s1.3: classifying the sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node.
Examples are: in the political party category, the distance vector of "positive clique a" is set to 1, and the distance vector of "negative clique B" is set to 3.
S2: and (3) voice recognition processing: carrying out voice recognition on the audio file to recognize sensitive words and related emotional words;
in step S2, the speech recognition processing includes the steps of:
s2.1: carrying out voice recognition on the audio file by utilizing a voice recognition engine, and converting the audio file into a text;
s2.2: completing the natural language processing procedures such as word segmentation, part of speech tagging, basic semantic recognition and the like, and storing the natural language processing procedures in a database;
s2.3: and identifying and marking the sensitive words and the related emotional words.
S3: and (3) positioning sensitive content: performing clustering analysis, identifying sensitive words and emotional words related to semantics, performing measurement calculation of related sensitive words and emotional words, and performing semantic judgment;
in a preferred embodiment, in step S3, the sensitive content locating step includes the following steps:
s3.1: performing clustering analysis, and identifying sensitive words and emotional words related to semantics;
s3.2: calculating the difference between the distance vectors of the sensitive words, and if the difference is smaller than a preset value, performing measurement calculation according to the time sequence and word sequence of the sensitive words and the emotional words so as to perform semantic correction; on the basis of a traditional semantic analysis algorithm, two key elements of time and distance vectors are introduced, and the accuracy of sensitive content identification is improved.
S3.3: and realizing the identification, positioning and labeling of sensitive content.
Examples are: the positive clique A has a plurality of defects which are typical negative (sensitive) contents, and the positive clique A overcomes the negative clique B because the negative clique B has a plurality of defects which are positive sentences.
In this example, by means of the conventional semantic analysis technology, if only two words, namely "front face group a" and "defect" are recognized and the early warning is performed, a large deviation exists.
An example of the judgment algorithm is as follows:
1. the relevant word vector: d (negative group B) -D (positive group A) < ═ 2, and semantic rule judgment is carried out;
2. metric (negative clique B-defect) ═ K1 (defect) -t (negative clique B)) + K2 (defect) -N (negative clique B))
metric (face group A-defect) ═ K1 (t (defect) -t (face group A)) + K2 (defect) -N (face group A))
Wherein: k1 and K2 are weighted distribution constants, and K1+ K2 is 1; t is the time sequence and N is the word sequence.
3. Comparing the two vector values, metric (positive clique a-disadvantage) > metric (negative clique B-disadvantage), indicates that (negative clique B) and (disadvantage) are more matched, resulting in correct semantics.
S4: outputting an analysis result: and outputting the sensitive content.
In step S4, the output of the analysis result includes the steps of:
s4.1: the user self-defines a threshold value aiming at the occurrence frequency of the sensitive words;
s4.2: the user self-defines an early warning output mode, including WeChat, short message, mail and webpage presentation;
s4.3: and labeling and tracing the sensitive content.
The embodiment provides a sensitive public opinion content identification method based on semantic analysis technology, and the method is characterized in that a sensitive word vector word library is established on the basis of a traditional natural language word library, and a vector distance relation is established among similar sensitive words. In the practical application field, for example, for real-time call content (information security field) or classroom teaching content (education technical field), sensitive content identification and early warning can be automatically carried out. The method can realize the judgment of sensitive semantics, greatly improve the accuracy and further realize the monitoring of sensitive public opinion content.
The method is applied to the field of information security, and can automatically identify the sensitive content analysis and early warning of real-time call. The results are applied to the technical field of education, and sensitive content analysis and early warning of classroom teaching contents can be achieved. The method is applied to the field of information security, and can automatically identify the sensitive content analysis of real-time conversation and perform early warning. The method is applied to the technical field of education, can realize sensitive content analysis of classroom teaching contents, and performs early warning. Especially, when the intelligent education system is applied to the ideological and political education class, the intelligent education system can accurately guide public opinions for controlling the ideological and political education in class, and has positive effects on vigorously promoting the mental civilization construction, promoting the healthy atmosphere in class and cultivating students with correct three views in China.
Example 2
A sensitive public opinion content early warning system based on semantic analysis technology comprises:
sensitive word bank: the system comprises a word library, a core word and distance vectors, wherein the word library is used for importing sensitive words, classifying the sensitive words, setting a core word as a reference word for each type of sensitive words, and setting the distance vectors from other similar words to the reference word by using the core word as a source node;
the voice recognition processing module: the voice recognition method is used for carrying out voice recognition on the audio file and recognizing sensitive words and related emotional words;
the sensitive content positioning module: the method is used for carrying out clustering analysis, identifying sensitive words and emotional words related to semantics and carrying out semantic correction;
and an output module of the analysis result: for outputting sensitive content.
The embodiment provides a sensitive public opinion content early warning system based on a semantic analysis technology, which realizes the identification, accurate analysis and output of sensitive content.
It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (3)
1. A sensitive public opinion content identification method based on semantic analysis technology is characterized by comprising the following steps:
s1: establishing a sensitive word vector library: importing a sensitive word vector library, classifying the sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node;
s2: and (3) voice recognition processing: carrying out voice recognition on the audio file to recognize sensitive words and related emotional words;
in step S2, the speech recognition processing includes the steps of:
s2.1: carrying out voice recognition on the audio file by utilizing a voice recognition engine, and converting the audio file into a text;
s2.2: completing word segmentation, part of speech tagging and basic semantic recognition, and storing the word segmentation, part of speech tagging and basic semantic recognition in a database;
s2.3: identifying and marking the sensitive words and the related emotional words;
s3: and (3) positioning sensitive content: performing clustering analysis, identifying sensitive words and emotional words related to semantics, and performing semantic analysis and judgment;
in step S3, the sensitive content locating method includes the following steps:
s3.1: performing clustering analysis, and identifying sensitive words and emotional words related to semantics;
s3.2: carrying out measurement calculation on the associated sensitive words and the emotional words;
in step S3.2, performing metric calculation of the associated sensitive words and the emotional words, specifically: calculating the difference between the distance vectors of the sensitive words, and if the difference is smaller than a preset value, performing measurement calculation according to the time sequence and word sequence of the sensitive words and the emotional words;
s3.3: realizing the identification, positioning and labeling of sensitive content;
s4: outputting an analysis result: outputting the sensitive content;
in step S4, the output of the analysis result includes the steps of:
s4.1: the user self-defines a threshold value aiming at the occurrence frequency of the sensitive words;
s4.2: the user self-defines an early warning output mode, including WeChat, short message, mail and webpage presentation;
s4.3: and labeling and tracing the sensitive content.
2. The method for identifying sensitive public opinion content based on semantic analysis technology as claimed in claim 1, wherein the step S1 of establishing a sensitive word library comprises the following steps:
s1.1: importing a Chinese word segmentation reference word library;
s1.2: establishing a special sensitive word vector word library;
s1.3: classifying the sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference word by using the core word as a source node.
3. A sensitive public opinion content early warning system based on semantic analysis technology is characterized by comprising:
sensitive word vector thesaurus: the method is used for importing a sensitive word vector word library in addition to a Chinese participle reference word library, classifying sensitive words, setting a core word as a reference word for each type of sensitive words, and setting distance vectors from other similar words to the reference words by using the core word as a source node;
the voice recognition processing module: the voice recognition method is used for carrying out voice recognition on the audio file and recognizing sensitive words and related emotional words; the method comprises the following steps: carrying out voice recognition on the audio file by utilizing a voice recognition engine, and converting the audio file into a text; completing word segmentation, part of speech tagging and basic semantic recognition, and storing the word segmentation, part of speech tagging and basic semantic recognition in a database; identifying and marking the sensitive words and the related emotional words;
the sensitive content positioning module: the method is used for carrying out clustering analysis and identifying sensitive words and emotional words related to semantics; performing measurement calculation on the associated sensitive words and the emotional words, specifically: calculating the difference between the distance vectors of the sensitive words, and if the difference is smaller than a preset value, performing measurement calculation according to the time sequence and word sequence of the sensitive words and the emotional words; realizing the identification, positioning and labeling of sensitive content;
and an output module of the analysis result: for outputting sensitive content; the method comprises the following steps: the user self-defines a threshold value aiming at the occurrence frequency of the sensitive words; the user self-defines an early warning output mode, including WeChat, short message, mail and webpage presentation; and labeling and tracing the sensitive content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710179529.8A CN107918633B (en) | 2017-03-23 | 2017-03-23 | Sensitive public opinion content identification method and early warning system based on semantic analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710179529.8A CN107918633B (en) | 2017-03-23 | 2017-03-23 | Sensitive public opinion content identification method and early warning system based on semantic analysis technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107918633A CN107918633A (en) | 2018-04-17 |
| CN107918633B true CN107918633B (en) | 2021-07-02 |
Family
ID=61898780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710179529.8A Active CN107918633B (en) | 2017-03-23 | 2017-03-23 | Sensitive public opinion content identification method and early warning system based on semantic analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107918633B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109446409A (en) * | 2018-09-19 | 2019-03-08 | 杭州安恒信息技术股份有限公司 | A kind of recognition methods of the target object of doubtful multiple level marketing behavior |
| CN109558480A (en) * | 2018-11-30 | 2019-04-02 | 重庆市千将软件有限公司 | For the counter method of crime of laundering behavior |
| CN109740053B (en) * | 2018-12-26 | 2021-03-05 | 广州灵聚信息科技有限公司 | Sensitive word shielding method and device based on NLP technology |
| CN109800600B (en) * | 2019-01-23 | 2020-11-24 | 中国海洋大学 | Ocean big data sensitivity evaluation system and prevention method facing privacy requirements |
| CN110765302A (en) * | 2019-09-20 | 2020-02-07 | 广州坚和网络科技有限公司 | Method for automatically managing and controlling mass user production content |
| CN112560472B (en) * | 2019-09-26 | 2023-07-11 | 腾讯科技（深圳）有限公司 | Method and device for identifying sensitive information |
| CN111128241A (en) * | 2019-12-30 | 2020-05-08 | 上海浩琨信息科技有限公司 | Intelligent quality inspection method and system for voice call |
| CN111581533B (en) * | 2020-05-12 | 2023-11-03 | 腾讯科技（深圳）有限公司 | Method and device for identifying state of target object, electronic equipment and storage medium |
| SE546022C2 (en) * | 2020-11-23 | 2024-04-16 | Assa Abloy Ab | Enabling training of a machine-learning model for trigger-word detection |
| CN112818700A (en) * | 2021-01-20 | 2021-05-18 | 广州明朝互动科技股份有限公司 | Sensitive information blocking method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090048998A (en) * | 2007-11-12 | 2009-05-15 | 주식회사 비즈모델라인 | System and method for alarming bad public opinion using keyword and recording medium |
| CN103049435A (en) * | 2013-01-04 | 2013-04-17 | 浙江工商大学 | Text fine granularity sentiment analysis method and text fine granularity sentiment analysis device |
| CN103207855A (en) * | 2013-04-12 | 2013-07-17 | 广东工业大学 | Fine-grained sentiment analysis system and method specific to product comment information |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| CN103559176A (en) * | 2012-10-29 | 2014-02-05 | 中国人民解放军国防科学技术大学 | Microblog emotional evolution analysis method and system |
| CN104951548A (en) * | 2015-06-24 | 2015-09-30 | 烟台中科网络技术研究所 | Method and system for calculating negative public opinion index |
| CN105740228A (en) * | 2016-01-25 | 2016-07-06 | 云南大学 | Internet public opinion analysis method |
| CN105809186A (en) * | 2016-02-25 | 2016-07-27 | 中国科学院声学研究所 | Emotion classification method and system |
| CN105824959A (en) * | 2016-03-31 | 2016-08-03 | 首都信息发展股份有限公司 | Public opinion monitoring method and system |
| CN106484846A (en) * | 2016-09-30 | 2017-03-08 | 广州特道信息科技有限公司 | A kind of monitoring method of network public-opinion big data |
-
2017
- 2017-03-23 CN CN201710179529.8A patent/CN107918633B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090048998A (en) * | 2007-11-12 | 2009-05-15 | 주식회사 비즈모델라인 | System and method for alarming bad public opinion using keyword and recording medium |
| CN103559176A (en) * | 2012-10-29 | 2014-02-05 | 中国人民解放军国防科学技术大学 | Microblog emotional evolution analysis method and system |
| CN103049435A (en) * | 2013-01-04 | 2013-04-17 | 浙江工商大学 | Text fine granularity sentiment analysis method and text fine granularity sentiment analysis device |
| CN103207855A (en) * | 2013-04-12 | 2013-07-17 | 广东工业大学 | Fine-grained sentiment analysis system and method specific to product comment information |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| CN104951548A (en) * | 2015-06-24 | 2015-09-30 | 烟台中科网络技术研究所 | Method and system for calculating negative public opinion index |
| CN105740228A (en) * | 2016-01-25 | 2016-07-06 | 云南大学 | Internet public opinion analysis method |
| CN105809186A (en) * | 2016-02-25 | 2016-07-27 | 中国科学院声学研究所 | Emotion classification method and system |
| CN105824959A (en) * | 2016-03-31 | 2016-08-03 | 首都信息发展股份有限公司 | Public opinion monitoring method and system |
| CN106484846A (en) * | 2016-09-30 | 2017-03-08 | 广州特道信息科技有限公司 | A kind of monitoring method of network public-opinion big data |
Non-Patent Citations (1)
| Title |
|---|
| 基于短文本情感分析的敏感信息识别;李杨;《西安交通大学学报》;20160930;第50卷(第9期);80-84 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107918633A (en) | 2018-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107918633B (en) | Sensitive public opinion content identification method and early warning system based on semantic analysis technology | |
| CN110277086B (en) | Voice synthesis method and system based on power grid dispatching knowledge graph and electronic equipment | |
| Wu et al. | Audio caption: Listen and tell | |
| CN106875941B (en) | Voice semantic recognition method of service robot | |
| CN110457689B (en) | Semantic processing method and related device | |
| CN110362819B (en) | Text emotion analysis method based on convolutional neural network | |
| CN112101045B (en) | Multi-mode semantic integrity recognition method and device and electronic equipment | |
| CN109388700A (en) | A kind of intension recognizing method and system | |
| CN107577662A (en) | Towards the semantic understanding system and method for Chinese text | |
| CN109165275B (en) | Intelligent substation operation ticket information intelligent search matching method based on deep learning | |
| CN104462064A (en) | Method and system for prompting content input in information communication of mobile terminals | |
| CN114298121A (en) | Multi-mode-based text generation method, model training method and device | |
| CN112580362A (en) | Visual behavior recognition method and system based on text semantic supervision and computer readable medium | |
| CN111651497A (en) | User label mining method and device, storage medium and electronic equipment | |
| CN114676255A (en) | Text processing method, device, equipment, storage medium and computer program product | |
| CN111159356A (en) | Knowledge graph construction method based on teaching content | |
| CN110414837A (en) | Based on mistake because of the man-machine interactive system of analysis | |
| CN113314150A (en) | Emotion recognition method and device based on voice data and storage medium | |
| CN113901289A (en) | Unsupervised learning-based recommendation method and system | |
| CN116010581A (en) | Knowledge graph question-answering method and system based on power grid hidden trouble shooting scene | |
| CN114444481B (en) | Sentiment analysis and generation method of news comment | |
| CN113486174B (en) | Model training, reading understanding method and device, electronic equipment and storage medium | |
| CN114090792A (en) | Document relation extraction method based on comparison learning and related equipment thereof | |
| CN112749556B (en) | Multi-language model training method and device, storage medium and electronic equipment | |
| CN113255829A (en) | Zero sample image target detection method and device based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 2108 and 2109, No. 563, lianggouling Road, Tianhe District, Guangzhou City, Guangdong Province (office only) Applicant after: GUANGZHOU THINK-HEIGHT INFORMATION TECHNOLOGY Co.,Ltd. Applicant after: SOUTH CHINA NORMAL University Address before: 510640 Guangdong city of Guangzhou province Tianhe District gold Yinglu No. 1 Jin Ying building room 1705 Applicant before: GUANGZHOU THINK-HEIGHT INFORMATION TECHNOLOGY Co.,Ltd. Applicant before: SOUTH CHINA NORMAL University |
|
| CB02 | Change of applicant information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zheng Kai Inventor after: Li Hao Inventor after: Huang Yemin Inventor after: Lin Nanhui Inventor before: Li Hao Inventor before: Lin Nanhui Inventor before: Zheng Kai Inventor before: Huang Yemin |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |